Archives/papers-we-love_papers-we-love
1
0
Fork 0
mirror of https://github.com/papers-we-love/papers-we-love.git synced 2025-06-13 12:54:28 +00:00
Code Issues Projects Releases Wiki Activity

Adding the HITS ALGORITHM Paper

Browse Source
This commit is contained in:
Khalian 2016-02-20 15:10:09 -05:00
parent b4aef294e1
commit 305a8395ff
1 changed files with 1 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
information_retrieval/README.md
View File

@ -47,16 +47,5 @@ The included documents are
* [:scroll:](hits.pdf) [Hits Algorithm](https://www.cs.cornell.edu/home/kleinber/auth.pdf) - Jon M. Kleinberg
This paper introduces the HITS algorithm, a link analysis algorithm that rates
webpages. Unlike the more famous page rank algorithm, the hits algorithm
makes a distinction between webpage behavior classifies them as hubs and authorities.
A page is authoratitative (in the sense the page has a large number of incoming links)
or acts as a hub (a directory of sort, which can be measured by the number of outgoing
link). The hits algorithm computes two scores for a page (authority and hub score)
where the algorithm iteratively computes the hub score as sum of authority scores of
outgoing links and authority scores as sum of hub scores of incoming links until a
convergence is attained. These scores can then be used to rank documents. While
this algorithm is famous in academia, its not very widely used in the industry
(a variant of this algorithm was used by a company called Teoma which was acquired
by AskJeeves)
This paper introduces the HITS algorithm, a link analysis algorithm that rates webpages. Unlike the more famous page rank algorithm, the hits algorithm makes a distinction between webpa`ge behavior classifies them as hubs and autho rities. A page is authoratitative (in the sense the page has a large number of incoming links) or acts as a hub (a directory of so rt, which can be measured b y the number of outgoing link). The hits algorithm computes two scores for a p age (authority and hub score) where the algorithm iteratively computes the hub score as sum of authority scores of outgoing links and authority scores as sum of hub scores of incoming links until a convergence is attained. These scores can then be used to rank documents. While this algorithm is famous in academia, its not very widely used in the industry (a variant of this algorithm was used by a company called Teoma which was acquired by AskJeeves)